为什么这个Theano代码成功运行没有任何错误?

时间:2015-10-13 11:24:29

标签: python numpy theano deep-learning

我从在线教程中借用了以下代码。我看到下面的代码写在代码的主要方法

c = broadcasted_add(a, b)

添加尺寸(2,1,2,2)的张量'a'和尺寸(2,2,2,2)的张量'b'。即使我们在make_tensor方法中声明adsable为'false',它如何才能正确添加?我们不应该将broadcastable声明为True,以便它可以添加不同的维度吗?不应该抛出尺寸不匹配的错误吗?我对播音的理解是错误的吗?

import numpy as np
from theano import function
import theano.tensor as T

def make_tensor(dim):
    """
    Returns a new Theano tensor with no broadcastable dimensions.
    dim: the total number of dimensions of the tensor.
    """

    return T.TensorType(broadcastable=tuple([False] * dim), dtype='float32')()

def broadcasted_add(a, b):
    """
    a: a 3D theano tensor
    b: a 4D theano tensor
    Returns c, a 4D theano tensor, where
    c[i, j, k, l] = a[l, k, i] + b[i, j, k, l]
    for all i, j, k, l
    """

return a.dimshuffle(2, 'x', 1, 0) + b

def partial_max(a):
    """
    a: a 4D theano tensor
    Returns b, a theano matrix, where
    b[i, j] = max_{k,l} a[i, k, l, j]
    for all i, j
    """

return a.max(axis=(1, 2))

if __name__ == "__main__":
    a = make_tensor(3)
    b = make_tensor(4)
    c = broadcasted_add(a, b)
    d = partial_max(c)

    f = function([a, b,], d)

    rng = np.random.RandomState([1, 2, 3])
    a_value = rng.randn(2, 2, 2).astype(a.dtype)
    b_value = rng.rand(2, 2, 2, 2).astype(b.dtype)
    c_value = np.transpose(a_value, (2, 1, 0))[:, None, :, :] + b_value
    expected = c_value.max(axis=1).max(axis=1)

    actual = f(a_value, b_value)

    assert np.allclose(actual, expected), (actual, expected)
    print "SUCCESS!"

1 个答案:

答案 0 :(得分:2)

这样做的原因是dimshuffle通过'x'参数值添加的新维度始终是可播放的。

请注意,在broadcasted_add中,唯一需要广播的维度是通过a添加到dimshuffle的维度。其他维度都不需要广播。